English(EN) MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation

新的AI模型实时生成高质量3D人体运动

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-28 04:00

研究人员开发了新的基于Transformer的框架，用于从文本生成高质量的3D人体运动。MOGO利用分层向量量化和单通道因果Transformer进行实时生成，展示了具有竞争力的质量和改进的性能。MotionHiFlow采用分层流匹配方法，逐步从粗粒度语义生成运动到精细的时间细节，并结合了跨尺度转换和显式结构建模以实现精确对齐。 AI

影响文本到运动生成方面的进展可以为游戏和电影中更逼真的虚拟环境和角色动画提供支持。

排序理由两篇新的研究论文介绍了用于文本到3D人体运动生成的新型基于Transformer的架构。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Dongjie Fu, Tengjiao Sun, Pengcheng Fang, Xiaohao Cai, Hansung Kim · 2026-05-05 04:00

MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation

arXiv:2506.05952v4 Announce Type: replace Abstract: Recent advances in transformer-based text-to-motion generation have led to impressive progress in synthesizing high-quality human motion. Nevertheless, jointly achieving high fidelity, streaming capability, real-time responsiven…
arXiv cs.CV TIER_1 English(EN) · Heng Li, Xiaotong Lin, Ling-An Zeng, Yulei Kang, Shuai Li, Jian-Fang Hu · 2026-04-28 04:00

MotionHiFlow: Text-to-motion via hierarchical flow matching

arXiv:2604.23264v1 Announce Type: new Abstract: Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich in fine-grained detail. Although recent approaches can produce complex and natura…

报道来源 [2]

MOGO: Residual Quantized Hierarchical Causal Transformer for High-Quality and Real-Time 3D Human Motion Generation

MotionHiFlow: Text-to-motion via hierarchical flow matching

相关实体

相关话题